Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{168136,
        author = {P ROJA and SK JAFAR AMEEN},
        title = {LOW POWER HIGH SPEED ACCURACY CONTROLLABLE APPROXIMATE MULTIPLIER DESIGN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {4},
        pages = {1408-1412},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=168136},
        abstract = {Many increasingly popular applications, such as image processing and recognition, are inherently tolerant of small inaccuracies. These applications are computationally demanding and multiplication is their fundamental arithmetic function, which creates an opportunity to trade off computational accuracy for reduced power consumption. Approximate computing is an efficient approach for error tolerant applications because it can trade off accuracy for power, and it currently plays an important role in such application domains. Different error-tolerant applications have different accuracy requirements, as do different program phases in an application. If multiplication accuracy is fixed, power will be wasted when high accuracy is not required. This means that approximate multipliers should be dynamically reconfigurable to match the different accuracy requirements of different program phases and applications. Approximate multiplication is considered to be an efficient technique for trading off energy against performance and accuracy. This work proposes an accuracy-controllable multiplier whose final product is generated by a carry-mask able adder. The proposed scheme can dynamically select the length of the carry propagation to satisfy the accuracy requirements flexibly. The partial product tree of the multiplier is approximated by the proposed tree compressor. An 8x8 multiplier design is implemented by employing the carry maskable adder and the compressor. Compared with a conventional Wallace tree multiplier, the proposed multiplier reduced power and critical path delay, depending on the required accuracy.},
        keywords = {Image Processing, Pattern Recognition, Machine Learning, Artificial Intelligence, Real-Time Embedded Systems},
        month = {September},
        }